In this task you will need to come up with categories to group the text together based on a goal, where each category can be described with a natural language predictate. For example

1. How are you doing?
2. How do I apply for visa?
3. Isn't it ridiculous?
4. How to get there by bus?
5. How is it going?
6. Aren't technological advancement good for the humanity?

Here is our goal: I want to cluster the questions based on their functionalities. Your responses are:
- "is a rhetorical quesiton"
- "is meant for greetings"
- "is asking for practically useful information"

(note that all of them need to be natural language predicates that can be validated on individual samples)

Here are some texts:

{samples_in_prompt}

Here is our goal: {goal} Please suggest me at most {num_descriptions_per_prompt} descriptions, one in a line, starting with "-" and surrounded by quotes"". In terms of formatting, each of them needs to be a predicate about a text, for example:
- "uses double negation"
- "has a conservative stance"

Do not output anything else. (Note that the examples might not be goal related, and your response should be both formatted correct as above and related to the goal.)
{example_description_in_prompt}

Again, here's the goal: {goal}. We also want the descriptions to be as diverse as possible. Your responses are:
- "